Classifying natural-language spatial relation terms with random forest algorithm

The exponential growth of natural language text data in social media has contributed a rich data source for geographic information. However, incorporating such data source for GIS analysis faces tremendous challenges as existing GIS data tend to be geometry based while natural language text data tend to rely on natural language spatial relation (NLSR) terms. To alleviate this problem, one critical step is to translate geometric configurations into NLSR terms, but existing methods to date (e.g. mean value or decision tree algorithm) are insufficient to obtain a precise translation. This study addresses this issue by adopting the random forest (RF) algorithm to automatically learn a robust mapping model from a large number of samples and to evaluate the importance of each variable for each NLSR term. Because the semantic similarity of the collected terms reduces the classification accuracy, different grouping schemes of NLSR terms are used, with their influences on classification results being evaluated. The experiment results demonstrate that the learned model can accurately transform geometric configurations into NLSR terms, and that recognizing different groups of terms require different sets of variables. More importantly, the results of variable importance evaluation indicate that the importance of topology types determined by the 9-intersection model is weaker than metric variables in defining NLSR terms, which contrasts to the assertion of ‘topology matters, metric refines’ in existing studies.     

Exploring Chile: Identities and Their Relation with the Environment through the Film Football Stories

Cinema can be considered a useful tool for understanding different geographic concepts, showing physical and human factors and the interactions between them. Andres Wood's film Football Stories explores the Chilean territory allowing the observation of the differences between the north and south of the country. Geographic components such as landscapes, architectures, the impact of anthropogenic activities, social inequalities, ways of life, and city and countryside differences are analyzed, as well as the importance of location, the spatial environment, and cinematic narration. The study of geography through films could contribute to understanding of our world and to spatial knowledge.     

Laboratory experiments on along-slope flows in homogeneous and stratified rotating fluids

Laboratory experiments have been carried out for the flow along isobaths of simulated shelf-continental slope geometry. Cases of both homogeneous and linearly stratified fluids are considered and the background flows are sufficiently strong to have the flow near the bottom boundary range from transitional to fully turbulent. The background motions are impulsively started and flows with a coast on the right (spin-down) and on the left (spin-up) are considered. The homogeneous spin-down and spin-up processes are smooth in the sense that no vortical structures were found to be of the order of the slope width or larger. Flows reach equilibrium more quickly for spin-down cases, and this is attributed to secondary flows forced by the basin geometry. All of the stratified experiments exhibited large-scale instabilities as evidenced by the generation of slope and basin scale eddy structures and a much slower decay than their homogeneous counterparts.